springboot+chatgpt+chatUI Pro开发智能聊天工具的实践
作者:奔跑中的小象
一、技术介绍
1.chatgpt-java是一个OpenAI的Java版SDK,支持开箱即用。目前以支持官网全部Api。支持最新版本GPT-3.5-Turbo模型以及whisper-1模型。
2.Spring Boot是由Pivotal团队提供的全新框架,其设计目的是用来简化新Spring应用的初始搭建以及开发过程。该框架使用了特定的方式来进行配置,从而使开发人员不再需要定义样板化的配置。通过这种方式,Spring Boot致力于在蓬勃发展的快速应用开发领域(rapid application development)成为领导者。
3.ChatUI Pro 是在ChatUI 基础组件的基础上,结合阿里小蜜的最佳实践,沉淀和总结出来的一个开箱即用的,可快速搭建智能对话机器人的框架。它简单易上手,通过简单的配置就能搭建出对话机器人;同时它强大易扩展,通过丰富的接口和自定义卡片满足各种定制化需求。
二、项目介绍
本项目采用了GPT-3.5-Turb模型作为基础,通过springboot结合redis、chat-java以及chatUI Pro实现简单的人工智能机器人。因为访问openAI的API返回结果比较慢,项目中当前端将问题请求发送到后端后,后端会将生成一个UUID,返回前端,同时后端也会重新开启一个线程去访问openAI,当openAI返回结果后,后端将UUID做为key,openAI返回的结果做为value存储到redis中。前端会根据后端第一次请求的结果中UUID做为参数每个5s请求一次后端的answer接口,answer接口会根据UUID查询redis是否有值,直到后端answer接口返回结果后前端将结果输出给用户
三、项目搭建
1.创建springboot项目,项目命名mychatgpt。
2.导入项目pom的依赖
<?xml version="1.0" encoding="UTF-8"?> <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd"> <modelVersion>4.0.0</modelVersion> <parent> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-starter-parent</artifactId> <version>2.5.12</version> <relativePath/> <!-- lookup parent from repository --> </parent> <groupId>com.xyh</groupId> <artifactId>mychatgpt</artifactId> <version>0.0.1-SNAPSHOT</version> <name>mychatgpt</name> <description>Demo project for Spring Boot</description> <properties> <java.version>8</java.version> </properties> <dependencies> <dependency> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-starter-data-redis</artifactId> </dependency> <dependency> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-starter-web</artifactId> </dependency> <dependency> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-starter-aop</artifactId> </dependency> <dependency> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-starter-test</artifactId> <exclusions> <exclusion> <groupId>org.apache.logging.log4j</groupId> <artifactId>log4j-api</artifactId> </exclusion> <exclusion> <groupId>org.apache.logging.log4j</groupId> <artifactId>log4j-to-slf4j</artifactId> </exclusion> </exclusions> <scope>test</scope> </dependency> <dependency> <groupId>org.projectlombok</groupId> <artifactId>lombok</artifactId> <optional>true</optional> </dependency> <dependency> <groupId>org.apache.httpcomponents</groupId> <artifactId>httpcore</artifactId> </dependency> <dependency> <groupId>com.theokanning.openai-gpt3-java</groupId> <artifactId>api</artifactId> <version>0.10.0</version> </dependency> <dependency> <groupId>com.theokanning.openai-gpt3-java</groupId> <artifactId>service</artifactId> <version>0.10.0</version> </dependency> <dependency> <groupId>com.theokanning.openai-gpt3-java</groupId> <artifactId>client</artifactId> <version>0.10.0</version> </dependency> <dependency> <groupId>cn.hutool</groupId> <artifactId>hutool-all</artifactId> <version>5.8.12</version> </dependency> <dependency> <groupId>com.unfbx</groupId> <artifactId>chatgpt-java</artifactId> <version>1.0.5</version> </dependency> <dependency> <groupId>mysql</groupId> <artifactId>mysql-connector-java</artifactId> <version>8.0.17</version> </dependency> <dependency> <groupId>com.alibaba</groupId> <artifactId>druid-spring-boot-starter</artifactId> <version>1.2.8</version> </dependency> <dependency> <groupId>com.baomidou</groupId> <artifactId>mybatis-plus-boot-starter</artifactId> <version>3.5.2</version> <exclusions> <exclusion> <groupId>com.baomidou</groupId> <artifactId>mybatis-plus-generator</artifactId> </exclusion> </exclusions> </dependency> <dependency> <groupId>com.github.yulichang</groupId> <artifactId>mybatis-plus-join</artifactId> <version>1.4.2</version> </dependency> <!--集成随机生成数据包 --> <dependency> <groupId>com.apifan.common</groupId> <artifactId>common-random</artifactId> <version>1.0.19</version> </dependency> <!--集成随机生成数据包 --> <dependency> <groupId>junit</groupId> <artifactId>junit</artifactId> <scope>test</scope> </dependency> </dependencies> <build> <plugins> <plugin> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-maven-plugin</artifactId> <configuration> <excludes> <exclude> <groupId>org.projectlombok</groupId> <artifactId>lombok</artifactId> </exclude> </excludes> </configuration> </plugin> </plugins> </build> </project>
3.编写chatGPT实现工具类
package com.xyh.mychatgpt.utils; import com.unfbx.chatgpt.OpenAiClient; import com.unfbx.chatgpt.entity.chat.ChatChoice; import com.unfbx.chatgpt.entity.chat.ChatCompletion; import com.unfbx.chatgpt.entity.chat.Message; import com.unfbx.chatgpt.entity.common.Choice; import com.unfbx.chatgpt.entity.completions.Completion; import org.springframework.beans.factory.annotation.Autowired; import org.springframework.beans.factory.annotation.Value; import org.springframework.stereotype.Component; import java.util.Arrays; import java.util.List; /** * @author xiangyuanhong * @description: TODO * @date 2023/3/21上午9:28 */ @Component public class ChatGPTUtils { @Value("${xyh.openai.key}") private String token; @Autowired private RedisUtils redisUtils; public void ask(String model,String question,String uuid){ StringBuffer result=new StringBuffer(); try { OpenAiClient openAiClient = new OpenAiClient(token, 3000, 300, 300, null); if("GPT-3.5-Turb".equals(model)){ // GPT-3.5-Turb模型 Message message=Message.builder().role(Message.Role.USER).content(question).build(); ChatCompletion chatCompletion = ChatCompletion.builder().messages(Arrays.asList(message)).build(); List<ChatChoice> resultList = openAiClient.chatCompletion(chatCompletion).getChoices(); for (int i = 0; i < resultList.size(); i++) { result.append(resultList.get(i).getMessage().getContent()); } }else{ //text-davinci-003/text-ada-003 Completion completion = Completion.builder() .prompt(question) .model(model) .maxTokens(2000) .temperature(0) .echo(false) .build(); Choice[] resultList = openAiClient.completions(completion).getChoices(); for (Choice choice : resultList) { result.append(choice.getText()); } } }catch (Exception e) { System.out.println(e.getMessage()); result.append("小爱还不太懂,回去一定努力学习补充知识"); } redisUtils.set(uuid,result.toString()); } }
4.开发项目Controller类,用来与前端进行交互
package com.xyh.mychatgpt.controller; import cn.hutool.core.thread.ThreadUtil; import cn.hutool.core.util.IdUtil; import cn.hutool.core.util.StrUtil; import com.xyh.mychatgpt.utils.ChatGPTUtils; import com.xyh.mychatgpt.utils.R; import com.xyh.mychatgpt.utils.RedisUtils; import org.springframework.beans.factory.annotation.Autowired; import org.springframework.web.bind.annotation.GetMapping; import org.springframework.web.bind.annotation.RestController; import javax.servlet.http.HttpServletRequest; /** * @author xiangyuanhong * @description: TODO * @date 2023/2/28下午4:57 */ @RestController public class IndexController { @Autowired private RedisUtils redisUtils; @Autowired private ChatGPTUtils chatGPTUtils; @GetMapping("/ask") public R ask(String question,HttpServletRequest request) { String uuid=IdUtil.simpleUUID(); if (StrUtil.isBlank(question)) { question = "今天天气怎么样?"; } String finalQuestion = question; ThreadUtil.execAsync(()->{ chatGPTUtils.ask("GPT-3.5-Turb", finalQuestion,uuid); }); return R.ok().put("data",uuid); } @GetMapping("/answer") public R answer(String uuid){ String result=redisUtils.get(uuid); return R.ok().put("data",result); } }
5.前端页面开发,在项目templates目录创建index.html页面,并引入chatUI pro相关文件
<!DOCTYPE html> <html lang="zh-CN"> <head> <meta name="renderer" content="webkit" /> <meta name="force-rendering" content="webkit" /> <meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1" /> <meta charset="UTF-8" /> <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=0, minimum-scale=1.0, maximum-scale=1.0, viewport-fit=cover" /> <title>滴答小爱</title> <link rel="stylesheet" href="//g.alicdn.com/chatui/sdk-v2/0.2.4/sdk.css" rel="external nofollow" > </head> <body> <div id="root"></div> <script src="//g.alicdn.com/chatui/sdk-v2/0.2.4/sdk.js"></script> <script src="//g.alicdn.com/chatui/extensions/0.0.7/isv-parser.js"></script> <script src="js/setup.js"></script> <script src="js/jquery-3.6.3.min.js"></script> <script src="//g.alicdn.com/chatui/icons/0.3.0/index.js" async></script> </body> </html>
6.创建setup.js实现chatUI Pro与后端通信交换。
var bot = new ChatSDK({ config: { // navbar: { // title: '滴答小爱' // }, robot: { avatar: 'images/chat.png' }, // 用户头像 user: { avatar: 'images/user.png', }, // 首屏消息 messages: [ { type: 'text', content: { text: '您好,小爱为您服务,请问有什么可以帮您的?' } } ], // 快捷短语 // quickReplies: [ // { name: '健康码颜色',isHighlight:true }, // { name: '入浙通行申报' }, // { name: '健康码是否可截图使用' }, // { name: '健康通行码适用范围' }, // ], // 输入框占位符 placeholder: '输入任何您想询问的问题', }, requests: { send: function (msg) { if (msg.type === 'text') { return { url: '/ask', data: { question: msg.content.text } }; } } }, handlers: { /** * * 解析请求返回的数据 * @param {object} res - 请求返回的数据 * @param {object} requestType - 请求类型 * @return {array} */ parseResponse: function (res, requestType) { // 根据 requestType 处理数据 if (requestType === 'send' && res.code==0) { // 用 isv 消息解析器处理数据 $.ajaxSettings.async=false; var answer=""; var isOK=false; while(!isOK){ $.get("/answer",{uuid:res.data},function(result){ console.log(result.data) if(null != result.data){ isOK=true; answer=result.data; } },"json"); if(!isOK){ sleep(5000); } } $.ajaxSettings.async=true; return [{"_id":res.data,type:"text",content:{text:answer},position:"left"}]; } }, }, }); function sleep(n) { //n表示的毫秒数 var start = new Date().getTime(); while (true) { if (new Date().getTime() - start > n) { break; } } } bot.run();
7.项目搭建完成后启动springboot项目然后访问http://ip:端口就可以。项目最终效果:http://hyrun.vip/
四、项目展示
到此这篇关于springboot+chatgpt+chatUI Pro开发智能聊天工具的实践的文章就介绍到这了,更多相关springboot chatgpt智能聊天内容请搜索脚本之家以前的文章或继续浏览下面的相关文章希望大家以后多多支持脚本之家!